@inproceedings{hessel-lee-2020-multimodal, title = "Does my multimodal model learn cross-modal interactions? It`s harder to tell than you might think!", author = "Hessel, Jack and Lee, Lillian", editor = "Webber, Bonnie and Cohn, Trevor and He, Yulan and Liu, Yang", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2020.emnlp-main.62/", doi = "10.18653/v1/2020.emnlp-main.62", pages = "861--877" }